Master's Theses

Date of Award

2016

Document Type

Thesis

Department

Computer Science

First Advisor

Jie Wei

Second Advisor

Akira Kawaguchi

Keywords

LDV, Machine learning, Vehicle classification

Abstract

Used as a non-invasive and remote sensor, the laser Doppler vibrometer (LDV) has been used in many different applications, such as inspection of aircrafts, bridge and structure and remote voice acquisition. However, using LDV as a vehicle surveillance device has not been feasible due to the lack of systematic investigations on its behavioral properties. In this thesis, the LDV data from different vehicles are examined and features are extracted. A tone-pitch indexing (TPI) scheme is developed to classify different vehicles by exploiting the engine’s periodic vibrations that are transferred throughout the vehicle’s body. Using the TPI with a two-layer feed-forward 20 intermediate-nodes neural network to classify vehicles’ engine, the results are encouraging as they can consistently achieve accuracies over 96%. However, the TPI required a length of 1.25 seconds of vibration, which is a drawback of the TPI, as vehicles generally are moving whence the 1.25 second signals are unavailable. Based on the success of TPI, a new normalized tone-pitch indexing (nTPI) scheme is further developed, using the engine’s periodic vibrations, and shortened the time period from 1.25 seconds to a reasonable 0.2 seconds. Keywords: LDV, Machine Learning, Neural network, Deep learning, Vehicle classification

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.